© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129039
    Prev
    Next
    INDEX
    Explanations

    references to standardization or standard metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    age
    -0.06
    pee
    -0.06
    ug
    -0.06
     Moody
    -0.06
    an
    -0.06
    do
    -0.06
    orman
    -0.06
    adi
    -0.06
    DO
    -0.06
    /print
    -0.06
    POSITIVE LOGITS
    ised
    0.15
    -issue
    0.14
    ization
    0.12
    bred
    0.12
    ize
    0.11
     dÄ±ÅŁÄ±
    0.11
    izing
    0.10
    ized
    0.10
    izes
    0.10
    isation
    0.10
    Activations Density 0.026%

    No Known Activations